Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Bang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ासत
    -0.09
    革
    -0.08
    äfte
    -0.08
     бизнеса
    -0.08
     неизвест
    -0.08
     vaše
    -0.08
     Cheap
    -0.08
     гиб
    -0.07
     небольш
    -0.07
     åt
    -0.07
    POSITIVE LOGITS
    literal
    0.09
    _literals
    0.09
     বিশ্ববিদ্যাল
    0.09
    Decimal
    0.09
    িগত
    0.09
    Literal
    0.08
     jacuzzi
    0.08
     বিজ্ঞান
    0.08
     Profess
    0.08
    _literal
    0.08
    Act Density 0.001%

    No Known Activations